README.md

---
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen3-VL-Reranker-2B
pipeline_tag: text-ranking
library_name: sentence-transformers
tags:
- reranking
- retrieval
- rag
- cross-encoder
- qwen3-vl
- pytorch
---

# **Supertron2-Reranker-2B: A Compact Cross-Encoder Reranking Model**

## **Model Description**

**Supertron2-Reranker-2B** is a reranking model built on top of [Qwen/Qwen3-VL-Reranker-2B](https://huggingface.co/Qwen/Qwen3-VL-Reranker-2B). It is designed to score query-document pairs for retrieval pipelines, search systems, and RAG applications where a stronger second-stage ranker is useful.

* **Developed by:** Surpem
* **Model type:** Cross-Encoder Reranker
* **Architecture:** Qwen3-VL reranker, 2B parameters
* **License:** Apache 2.0

---

## **Capabilities**

### **Search Reranking**

Supertron2-Reranker-2B can compare a user query against candidate passages and assign relevance scores. It is intended as a second-stage reranker after a faster retriever has already selected candidate documents.

### **RAG Pipelines**

The model can help improve retrieval-augmented generation by pushing more relevant documents toward the top of the context window before answer generation.

### **Question-Document Matching**

Supertron2-Reranker-2B is useful for matching questions to passages, snippets, help-center articles, documentation chunks, and other text candidates.

### **Instruction-Aware Retrieval**

The model is prompted for relevance scoring, making it suitable for natural language search tasks where query intent matters.

---

## **Get Started**

```python
from sentence_transformers import CrossEncoder

model_id = "Surpem/Supertron2-Reranker-2B"

model = CrossEncoder(model_id)

pairs = [
    ("What is the capital of France?", "Paris is the capital and largest city of France."),
    ("What is the capital of France?", "Mars is often called the red planet."),
]

scores = model.predict(pairs)
print(scores)
```

Example reranking:

```python
query = "How do I reset my password?"
documents = [
    "Use the account recovery page to reset your password.",
    "Our refund policy allows returns within 30 days.",
    "Two-factor authentication adds extra login security.",
]

results = model.rank(query, documents)
print(results)
```

---

## **Hardware Requirements**

| Precision | Min VRAM | Recommended |
|---|---|---|
| bfloat16 | 6 GB | 10 GB+ |
| 4-bit quantized | 3 GB | 6 GB+ |

For larger batches or long documents, use more VRAM or reduce the batch size/max sequence length.

---

## **Intended Use**

Supertron2-Reranker-2B is intended for:

* Search reranking
* RAG document reranking
* Query-passage relevance scoring
* Documentation and knowledge-base retrieval
* Evaluation of candidate retrieval results

It is not intended to be used as a standalone chat model.

---

## **Limitations**

* The model scores relevance; it does not generate answers.
* It should be evaluated on your own retrieval domain before production use.
* Long documents may need chunking before reranking.
* Relevance scores are relative and may not be calibrated across unrelated queries.
* The model may still rank incorrect, outdated, or unsafe content highly if it appears textually relevant.

---

## **Citation**

```bibtex
@misc{surpem2026supertron2-reranker-2b,
      title={Supertron2-Reranker-2B -- Compact Cross-Encoder Reranking Model},
      author={Surpem},
      year={2026},
      url={https://huggingface.co/Surpem/Supertron2-Reranker-2B},
}
```